Tagged:

2 posts

• When AI Writes the Bug: Security Vulnerabilities in LLM-Generated Code

  Peer-reviewed studies confirm that AI code assistants produce insecure code at high rates — and that developers using them write less secure code on average. Here's which CWE classes recur, why they recur, and what effective review looks like.

  Jul 9, 2026 llm-generated-code code-security cwe code-review ai-code-assistants sast devsecops

• CI/CD Pipeline Injection: When AI Code Assistants Become Supply Chain Threats

  AI coding assistants consume your codebase as context — and that context is attacker-controllable. This post maps the attack surface: indirect prompt injection via poisoned READMEs, hallucinated package names that resolve to malicious code, AI-generated tests that exfiltrate secrets, and training data poisoning that shifts model behavior at the corpus level.

  Jul 3, 2026 supply-chain prompt-injection ai-code-assistants ci-cd-security threat-modeling defense-patterns